Introduction to AI

Gary Geunbae Lee, Eng 2-211, gblee@postech.ac.kr, 279-2254

1.  Course objectives

This course teaches basic knowledge of modern AI including heuristics search and problem solving, logics and knowledge representation, probabilistic and bayesian reasoning, MDP and reinforcement learning, machine learning and neural networks, and several applications such as vision, NLP, robotics, etc.

2. Course prerequisites

no required pre-requisite

3. Grading

midterm 35%

 final 35%

 3-4 (programming) assignments  30%

 4  texts or references 

 Artificial Intelligence: A Modern Approach, 4th ed. by Stuart Russell (UC Berkeley) and Peter Norvig (Google).

 5. Others

    instruction language: English

    the 3-4 assignments will be for solving (including programming) several interesting AI problems (every 4-5 weeks)

6. Course schedule & Material 

*Most of the slides come from Berkeley AI course-CS188 which are available at http://ai.berkeley.edu

• Introduction

• Heuristic search

• Constraint satisfaction problem

• Game search

• Markov decision process

• Reinforcement learning

• Logic

• Knowledge representation

• Symbolic planning

• Probability

• Bayesian network

• Bayesian inference

• Decision network

• Hidden markov model

• ML-Naïve bayes

• Neural network

• Decision tree

• Kernels and clustering

• Applications